Deep Multi-Task and Meta Learning | Comprehensive Guide

In-depth understanding of state-of-the-art multi-task learning and meta-learning algorithms for few-shot learning, transfer learning, and lifelong learning.

Introduction

A comprehensive guide to deep multi-task and meta learning by Chelsea Finn.

Highlights

• Covers self-supervised pre-training for downstream few-shot learning and transfer learning
• Discusses meta-learning methods that aim to learn efficient learning algorithms that can learn new tasks quickly
• Explores curriculum and lifelong learning, where the problem requires learning a sequence of tasks, leveraging their shared structure to enable knowledge transfer

Recommendation

This graduate-level course provides an in-depth understanding of the state-of-the-art multi-task learning and meta-learning algorithms, preparing students to conduct research on these topics.